Related papers: Featureless: Bypassing feature extraction in actio…

Scientific observations may consist of a large number of variables (features). Identifying a subset of meaningful features is often ignored in unsupervised learning, despite its potential for unraveling clear patterns hidden in the ambient…

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data…

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a…

In computer vision, action recognition refers to the act of classifying an action that is present in a given video and action detection involves locating actions of interest in space and/or time. Videos, which contain photometric…

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…

Time series classification is an important task in its own right, and it is often a precursor to further downstream analytics. To date, virtually all works in the literature have used either shape-based classification using a distance…

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…

Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the…

Many real-world optimization problems contain parameters that are unknown before deployment time, either due to stochasticity or to lack of information (e.g., demand or travel times in delivery problems). A common strategy in such cases is…

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…

We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an…

Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of…

We present an approach for weakly supervised learning of human actions from video transcriptions. Our system is based on the idea that, given a sequence of input data and a transcript, i.e. a list of the order the actions occur in the…

Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these…

Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of…

Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative…